Training speed and results

[litingsjj]

Sorry to bother you, I have two question about this project. for training work, I use multi gpus, the speed about 1.79it/s in first two epoch, it takes one day. After that, the speed is so fast, I don't know why this happened. Also the result, the detections repeatability is more better than rpautrat/Superpoint's, but the descriptors: hpatches-i is 0.90. hpatches-v is 0.55. Compare with rpautrat/Superpoint's, the result is not good.

[shaofengzeng]

Thanks for your attention. I have no idea about the speed. It is similar to my training process. I guess the detector loss causes this phenomenon

The default hyper-parameters may not work well, you have to adjust them several times to get better results. The latest version adds two important variables, i.e., positive_dist, negative_dist, to help you fine tune the model. The parameters lambda_d, lambda_loss, positive_margin and negative_margin are the most decisive ones. You need to adjust them to make positive_dist and negative_dist as small as possible. (The weight i released in the latest version can achieve 0.66 acc. on hpatches_v)

[litingsjj]

Thx much with your reply! I will try finetune these parameters! 0.66 acc for hpatches-v is your best result? Also, is the result use pretrain model(superpoint_bn.pth)?

[shaofengzeng]

Thx much with your reply! I will try finetune these parameters! 0.66 acc for hpatches-v is your best result? Also, is the result use pretrain model(superpoint_bn.pth)?

I trained the model without any pre-trained model, and it cost me several days to achieve this performance. Training the model really needs experience and tricks. And i'm failed to find a better hyper-parameters that can directly obtain a good model. 0.66 may not be the best, but this is the best model i can get right now.

[litingsjj]

Got it! thx again!

[litingsjj]

my result never reach 0.60 for hpatches-v when try several hyper-parameters, can you share hyper-parameters with superpoint_bn.pth? because I inference this model, the result hpatches-v is 0.66. Also if you get better result that can share the experience. I will so appreciate!

[shaofengzeng]

If you want to run with superpoint_bn.pth, remember to set eps=1e-3 for all BatchNorm2d in backbone.py and cnn_head.py. Moreover, another parameter, i.e., momentum , may also work for superpoint_bn.pth (set momentum=0.01), you can try.

[litingsjj]

Actually, I get 0.66 result when set eps=1e-3 and momentum=0.1 for inference. But when I training without any pre-trained model, how to set those hyper-parameters to get this result? I try to set eps=1e-3, lambda_d=250 and lambda_loss=10 or other val, fix lr... It can't get this result

[shaofengzeng]

momentum=0.01 and eps=1e-3 are for BatchNorm2d, and only work for superpoint_bn.pth, which is converted from rpautrat's superpoint.
If you want to train your model using this pytorch scripts, i suggest you remove the parameters eps and momentum in BatchNorm2d
sp_0.pth is the model i trained without any pretrained weight.
As far as i know, this pytorch version is very sensitive to the parameters lambda_d and lambda_loss. A bigger lambda_d will make the model more stable，however，the performance is not good.

[litingsjj]

Thanks! Ihave a last question about README.md -> Steps. Is that means training model need two stage? The firsts stage need 2.Commet the following lines in loss.py and Set base_lr=0.01 , than use trained models train stage two: base_lr=0.001 and fix hyper-parameters:lambda_d = 250 #balance positive_dist and negtive_dist lambda_loss = 10 #balance detector loss and descriptor loss
The 7.Start training again.(lambda_d and lambda_loss may need to be adjusted several times). is means fix hyper-parameters several times to train model?(maybe stage three, stage four?)

[litingsjj]

If I use your last version, should I train how many times?

[litingsjj]

Also, converted from rpautrat's superpoint didn't have same result, Is possible have bug like this: rpautrat/SuperPoint#117
eric-yyjau/pytorch-superpoint#24

[shaofengzeng]

Set eps=1e-3 for BN will achieve 0.66 acc. on hpatches-v. I'm not sure if you can achieve similar performances by setting eps=1e-3, momentum=0.01. Because the default parameters of BN between tf and torch are different, eps and momentum are two key parameters. Moreover, the conv2d in tf and pytorch are also slightly different. So we can only get similar performances as the rpautrat's sp.
I'm not sure how many times you need to train. Right now, i haven't got an effective training process. However, i strongly suggest you reading the descriptor_loss functions in loss.py and debugging some of the key variables like dot_product_desc, positive_dist, negtive_dist. I think this will greatly help you adjust the hyper-parameters

[litingsjj]

Thanks for your answer!